diff options
Diffstat (limited to 'arch/mips')
39 files changed, 737 insertions, 440 deletions
diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c index 58fca9a..3446b6f 100644 --- a/arch/mips/ar7/platform.c +++ b/arch/mips/ar7/platform.c @@ -576,6 +576,7 @@ static int __init ar7_register_uarts(void) uart_port.type = PORT_AR7; uart_port.uartclk = clk_get_rate(bus_clk) / 2; uart_port.iotype = UPIO_MEM32; + uart_port.flags = UPF_FIXED_TYPE; uart_port.regshift = 2; uart_port.line = 0; @@ -654,6 +655,10 @@ static int __init ar7_register_devices(void) u32 val; int res; + res = ar7_gpio_init(); + if (res) + pr_warn("unable to register gpios: %d\n", res); + res = ar7_register_uarts(); if (res) pr_err("unable to setup uart(s): %d\n", res); diff --git a/arch/mips/ar7/prom.c b/arch/mips/ar7/prom.c index a23adc4..36aabee 100644 --- a/arch/mips/ar7/prom.c +++ b/arch/mips/ar7/prom.c @@ -246,8 +246,6 @@ void __init prom_init(void) ar7_init_cmdline(fw_arg0, (char **)fw_arg1); ar7_init_env((struct env_var *)fw_arg2); console_config(); - - ar7_gpio_init(); } #define PORT(offset) (KSEG1ADDR(AR7_REGS_UART0 + (offset * 4))) diff --git a/arch/mips/ath79/clock.c b/arch/mips/ath79/clock.c index cc3a1e3..7e2bb12 100644 --- a/arch/mips/ath79/clock.c +++ b/arch/mips/ath79/clock.c @@ -508,16 +508,19 @@ static void __init ath79_clocks_init_dt_ng(struct device_node *np) ar9330_clk_init(ref_clk, pll_base); else { pr_err("%s: could not find any appropriate clk_init()\n", dnfn); - goto err_clk; + goto err_iounmap; } if (of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data)) { pr_err("%s: could not register clk provider\n", dnfn); - goto err_clk; + goto err_iounmap; } return; +err_iounmap: + iounmap(pll_base); + err_clk: clk_put(ref_clk); diff --git a/arch/mips/dec/int-handler.S b/arch/mips/dec/int-handler.S index 1910223..cea2bb1 100644 --- a/arch/mips/dec/int-handler.S +++ b/arch/mips/dec/int-handler.S @@ -147,23 +147,12 @@ * Find irq with highest priority */ # open coded PTR_LA t1, cpu_mask_nr_tbl -#if (_MIPS_SZPTR == 32) +#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32) # open coded la t1, cpu_mask_nr_tbl lui t1, %hi(cpu_mask_nr_tbl) addiu t1, %lo(cpu_mask_nr_tbl) - -#endif -#if (_MIPS_SZPTR == 64) - # open coded dla t1, cpu_mask_nr_tbl - .set push - .set noat - lui t1, %highest(cpu_mask_nr_tbl) - lui AT, %hi(cpu_mask_nr_tbl) - daddiu t1, t1, %higher(cpu_mask_nr_tbl) - daddiu AT, AT, %lo(cpu_mask_nr_tbl) - dsll t1, 32 - daddu t1, t1, AT - .set pop +#else +#error GCC `-msym32' option required for 64-bit DECstation builds #endif 1: lw t2,(t1) nop @@ -214,23 +203,12 @@ * Find irq with highest priority */ # open coded PTR_LA t1,asic_mask_nr_tbl -#if (_MIPS_SZPTR == 32) +#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32) # open coded la t1, asic_mask_nr_tbl lui t1, %hi(asic_mask_nr_tbl) addiu t1, %lo(asic_mask_nr_tbl) - -#endif -#if (_MIPS_SZPTR == 64) - # open coded dla t1, asic_mask_nr_tbl - .set push - .set noat - lui t1, %highest(asic_mask_nr_tbl) - lui AT, %hi(asic_mask_nr_tbl) - daddiu t1, t1, %higher(asic_mask_nr_tbl) - daddiu AT, AT, %lo(asic_mask_nr_tbl) - dsll t1, 32 - daddu t1, t1, AT - .set pop +#else +#error GCC `-msym32' option required for 64-bit DECstation builds #endif 2: lw t2,(t1) nop diff --git a/arch/mips/include/asm/branch.h b/arch/mips/include/asm/branch.h index de781cf..da80878 100644 --- a/arch/mips/include/asm/branch.h +++ b/arch/mips/include/asm/branch.h @@ -74,10 +74,7 @@ static inline int compute_return_epc(struct pt_regs *regs) return __microMIPS_compute_return_epc(regs); if (cpu_has_mips16) return __MIPS16e_compute_return_epc(regs); - return regs->cp0_epc; - } - - if (!delay_slot(regs)) { + } else if (!delay_slot(regs)) { regs->cp0_epc += 4; return 0; } diff --git a/arch/mips/include/asm/irq.h b/arch/mips/include/asm/irq.h index 956db6e..c5d3517 100644 --- a/arch/mips/include/asm/irq.h +++ b/arch/mips/include/asm/irq.h @@ -18,9 +18,24 @@ #include <irq.h> #define IRQ_STACK_SIZE THREAD_SIZE +#define IRQ_STACK_START (IRQ_STACK_SIZE - 16) extern void *irq_stack[NR_CPUS]; +/* + * The highest address on the IRQ stack contains a dummy frame put down in + * genex.S (handle_int & except_vec_vi_handler) which is structured as follows: + * + * top ------------ + * | task sp | <- irq_stack[cpu] + IRQ_STACK_START + * ------------ + * | | <- First frame of IRQ context + * ------------ + * + * task sp holds a copy of the task stack pointer where the struct pt_regs + * from exception entry can be found. + */ + static inline bool on_irq_stack(int cpu, unsigned long sp) { unsigned long low = (unsigned long)irq_stack[cpu]; diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h index 2e41807..b6845db 100644 --- a/arch/mips/include/asm/mips-cm.h +++ b/arch/mips/include/asm/mips-cm.h @@ -239,8 +239,8 @@ BUILD_CM_Cx_R_(tcid_8_priority, 0x80) #define CM_GCR_BASE_GCRBASE_MSK (_ULCAST_(0x1ffff) << 15) #define CM_GCR_BASE_CMDEFTGT_SHF 0 #define CM_GCR_BASE_CMDEFTGT_MSK (_ULCAST_(0x3) << 0) -#define CM_GCR_BASE_CMDEFTGT_DISABLED 0 -#define CM_GCR_BASE_CMDEFTGT_MEM 1 +#define CM_GCR_BASE_CMDEFTGT_MEM 0 +#define CM_GCR_BASE_CMDEFTGT_RESERVED 1 #define CM_GCR_BASE_CMDEFTGT_IOCU0 2 #define CM_GCR_BASE_CMDEFTGT_IOCU1 3 diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index 4be2763..bfff6ea 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -103,6 +103,7 @@ void output_thread_info_defines(void) DEFINE(_THREAD_SIZE, THREAD_SIZE); DEFINE(_THREAD_MASK, THREAD_MASK); DEFINE(_IRQ_STACK_SIZE, IRQ_STACK_SIZE); + DEFINE(_IRQ_STACK_START, IRQ_STACK_START); BLANK(); } diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c index c86b66b..c3f2fb3 100644 --- a/arch/mips/kernel/branch.c +++ b/arch/mips/kernel/branch.c @@ -399,7 +399,7 @@ int __MIPS16e_compute_return_epc(struct pt_regs *regs) * * @regs: Pointer to pt_regs * @insn: branch instruction to decode - * @returns: -EFAULT on error and forces SIGBUS, and on success + * @returns: -EFAULT on error and forces SIGILL, and on success * returns 0 or BRANCH_LIKELY_TAKEN as appropriate after * evaluating the branch. * @@ -431,7 +431,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, /* Fall through */ case jr_op: if (NO_R6EMU && insn.r_format.func == jr_op) - goto sigill_r6; + goto sigill_r2r6; regs->cp0_epc = regs->regs[insn.r_format.rs]; break; } @@ -446,7 +446,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, switch (insn.i_format.rt) { case bltzl_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bltz_op: if ((long)regs->regs[insn.i_format.rs] < 0) { epc = epc + 4 + (insn.i_format.simmediate << 2); @@ -459,7 +459,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bgezl_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bgez_op: if ((long)regs->regs[insn.i_format.rs] >= 0) { epc = epc + 4 + (insn.i_format.simmediate << 2); @@ -473,10 +473,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bltzal_op: case bltzall_op: if (NO_R6EMU && (insn.i_format.rs || - insn.i_format.rt == bltzall_op)) { - ret = -SIGILL; - break; - } + insn.i_format.rt == bltzall_op)) + goto sigill_r2r6; regs->regs[31] = epc + 8; /* * OK we are here either because we hit a NAL @@ -507,10 +505,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bgezal_op: case bgezall_op: if (NO_R6EMU && (insn.i_format.rs || - insn.i_format.rt == bgezall_op)) { - ret = -SIGILL; - break; - } + insn.i_format.rt == bgezall_op)) + goto sigill_r2r6; regs->regs[31] = epc + 8; /* * OK we are here either because we hit a BAL @@ -556,6 +552,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, /* * These are unconditional and in j_format. */ + case jalx_op: case jal_op: regs->regs[31] = regs->cp0_epc + 8; case j_op: @@ -573,7 +570,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, */ case beql_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case beq_op: if (regs->regs[insn.i_format.rs] == regs->regs[insn.i_format.rt]) { @@ -587,7 +584,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bnel_op: if (NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bne_op: if (regs->regs[insn.i_format.rs] != regs->regs[insn.i_format.rt]) { @@ -601,7 +598,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case blezl_op: /* not really i_format */ if (!insn.i_format.rt && NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case blez_op: /* * Compact branches for R6 for the @@ -636,7 +633,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case bgtzl_op: if (!insn.i_format.rt && NO_R6EMU) - goto sigill_r6; + goto sigill_r2r6; case bgtz_op: /* * Compact branches for R6 for the @@ -774,35 +771,27 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, #else case bc6_op: /* Only valid for MIPS R6 */ - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; regs->cp0_epc += 8; break; case balc6_op: - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; /* Compact branch: BALC */ regs->regs[31] = epc + 4; epc += 4 + (insn.i_format.simmediate << 2); regs->cp0_epc = epc; break; case pop66_op: - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; /* Compact branch: BEQZC || JIC */ regs->cp0_epc += 8; break; case pop76_op: - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; /* Compact branch: BNEZC || JIALC */ if (!insn.i_format.rs) { /* JIALC: set $31/ra */ @@ -814,10 +803,8 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, case pop10_op: case pop30_op: /* Only valid for MIPS R6 */ - if (!cpu_has_mips_r6) { - ret = -SIGILL; - break; - } + if (!cpu_has_mips_r6) + goto sigill_r6; /* * Compact branches: * bovc, beqc, beqzalc, bnvc, bnec, bnezlac @@ -831,11 +818,17 @@ int __compute_return_epc_for_insn(struct pt_regs *regs, return ret; sigill_dsp: - printk("%s: DSP branch but not DSP ASE - sending SIGBUS.\n", current->comm); - force_sig(SIGBUS, current); + pr_info("%s: DSP branch but not DSP ASE - sending SIGILL.\n", + current->comm); + force_sig(SIGILL, current); + return -EFAULT; +sigill_r2r6: + pr_info("%s: R2 branch but r2-to-r6 emulator is not present - sending SIGILL.\n", + current->comm); + force_sig(SIGILL, current); return -EFAULT; sigill_r6: - pr_info("%s: R2 branch but r2-to-r6 emulator is not preset - sending SIGILL.\n", + pr_info("%s: R6 branch but no MIPSr6 ISA support - sending SIGILL.\n", current->comm); force_sig(SIGILL, current); return -EFAULT; diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S index 59476a6..a00e87b 100644 --- a/arch/mips/kernel/cps-vec.S +++ b/arch/mips/kernel/cps-vec.S @@ -361,7 +361,7 @@ LEAF(mips_cps_get_bootcfg) END(mips_cps_get_bootcfg) LEAF(mips_cps_boot_vpes) - PTR_L ta2, COREBOOTCFG_VPEMASK(a0) + lw ta2, COREBOOTCFG_VPEMASK(a0) PTR_L ta3, COREBOOTCFG_VPECONFIG(a0) #if defined(CONFIG_CPU_MIPSR6) diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S index 7791840..db07793 100644 --- a/arch/mips/kernel/entry.S +++ b/arch/mips/kernel/entry.S @@ -11,6 +11,7 @@ #include <asm/asm.h> #include <asm/asmmacro.h> #include <asm/compiler.h> +#include <asm/irqflags.h> #include <asm/regdef.h> #include <asm/mipsregs.h> #include <asm/stackframe.h> @@ -137,6 +138,7 @@ work_pending: andi t0, a2, _TIF_NEED_RESCHED # a2 is preloaded with TI_FLAGS beqz t0, work_notifysig work_resched: + TRACE_IRQS_OFF jal schedule local_irq_disable # make sure need_resched and @@ -173,6 +175,7 @@ syscall_exit_work: beqz t0, work_pending # trace bit set? local_irq_enable # could let syscall_trace_leave() # call schedule() instead + TRACE_IRQS_ON move a0, sp jal syscall_trace_leave b resume_userspace diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index 2ac6c26..ae810da 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -215,9 +215,11 @@ NESTED(handle_int, PT_SIZE, sp) beq t0, t1, 2f /* Switch to IRQ stack */ - li t1, _IRQ_STACK_SIZE + li t1, _IRQ_STACK_START PTR_ADD sp, t0, t1 + /* Save task's sp on IRQ stack so that unwinding can follow it */ + LONG_S s1, 0(sp) 2: jal plat_irq_dispatch @@ -325,9 +327,11 @@ NESTED(except_vec_vi_handler, 0, sp) beq t0, t1, 2f /* Switch to IRQ stack */ - li t1, _IRQ_STACK_SIZE + li t1, _IRQ_STACK_START PTR_ADD sp, t0, t1 + /* Save task's sp on IRQ stack so that unwinding can follow it */ + LONG_S s1, 0(sp) 2: jalr v0 diff --git a/arch/mips/kernel/head.S b/arch/mips/kernel/head.S index cf05220..d1bb506 100644 --- a/arch/mips/kernel/head.S +++ b/arch/mips/kernel/head.S @@ -106,8 +106,8 @@ NESTED(kernel_entry, 16, sp) # kernel entry point beq t0, t1, dtb_found #endif li t1, -2 - beq a0, t1, dtb_found move t2, a1 + beq a0, t1, dtb_found li t2, 0 dtb_found: diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c index 7cf653e..60c4d45 100644 --- a/arch/mips/kernel/pm-cps.c +++ b/arch/mips/kernel/pm-cps.c @@ -56,7 +56,6 @@ DECLARE_BITMAP(state_support, CPS_PM_STATE_COUNT); * state. Actually per-core rather than per-CPU. */ static DEFINE_PER_CPU_ALIGNED(u32*, ready_count); -static DEFINE_PER_CPU_ALIGNED(void*, ready_count_alloc); /* Indicates online CPUs coupled with the current CPU */ static DEFINE_PER_CPU_ALIGNED(cpumask_t, online_coupled); @@ -642,7 +641,6 @@ static int cps_pm_online_cpu(unsigned int cpu) { enum cps_pm_state state; unsigned core = cpu_data[cpu].core; - unsigned dlinesz = cpu_data[cpu].dcache.linesz; void *entry_fn, *core_rc; for (state = CPS_PM_NC_WAIT; state < CPS_PM_STATE_COUNT; state++) { @@ -662,16 +660,11 @@ static int cps_pm_online_cpu(unsigned int cpu) } if (!per_cpu(ready_count, core)) { - core_rc = kmalloc(dlinesz * 2, GFP_KERNEL); + core_rc = kmalloc(sizeof(u32), GFP_KERNEL); if (!core_rc) { pr_err("Failed allocate core %u ready_count\n", core); return -ENOMEM; } - per_cpu(ready_count_alloc, core) = core_rc; - - /* Ensure ready_count is aligned to a cacheline boundary */ - core_rc += dlinesz - 1; - core_rc = (void *)((unsigned long)core_rc & ~(dlinesz - 1)); per_cpu(ready_count, core) = core_rc; } diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c index 4eff2ae..4c01ee5 100644 --- a/arch/mips/kernel/proc.c +++ b/arch/mips/kernel/proc.c @@ -83,7 +83,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) } seq_printf(m, "isa\t\t\t:"); - if (cpu_has_mips_r1) + if (cpu_has_mips_1) seq_printf(m, " mips1"); if (cpu_has_mips_2) seq_printf(m, "%s", " mips2"); diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index fbbf5fc..c558bce 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -50,9 +50,7 @@ #ifdef CONFIG_HOTPLUG_CPU void arch_cpu_idle_dead(void) { - /* What the heck is this check doing ? */ - if (!cpumask_test_cpu(smp_processor_id(), &cpu_callin_map)) - play_dead(); + play_dead(); } #endif @@ -487,31 +485,52 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page, unsigned long pc, unsigned long *ra) { + unsigned long low, high, irq_stack_high; struct mips_frame_info info; unsigned long size, ofs; + struct pt_regs *regs; int leaf; - extern void ret_from_irq(void); - extern void ret_from_exception(void); if (!stack_page) return 0; /* - * If we reached the bottom of interrupt context, - * return saved pc in pt_regs. + * IRQ stacks start at IRQ_STACK_START + * task stacks at THREAD_SIZE - 32 */ - if (pc == (unsigned long)ret_from_irq || - pc == (unsigned long)ret_from_exception) { - struct pt_regs *regs; - if (*sp >= stack_page && - *sp + sizeof(*regs) <= stack_page + THREAD_SIZE - 32) { - regs = (struct pt_regs *)*sp; - pc = regs->cp0_epc; - if (!user_mode(regs) && __kernel_text_address(pc)) { - *sp = regs->regs[29]; - *ra = regs->regs[31]; - return pc; - } + low = stack_page; + if (!preemptible() && on_irq_stack(raw_smp_processor_id(), *sp)) { + high = stack_page + IRQ_STACK_START; + irq_stack_high = high; + } else { + high = stack_page + THREAD_SIZE - 32; + irq_stack_high = 0; + } + + /* + * If we reached the top of the interrupt stack, start unwinding + * the interrupted task stack. + */ + if (unlikely(*sp == irq_stack_high)) { + unsigned long task_sp = *(unsigned long *)*sp; + + /* + * Check that the pointer saved in the IRQ stack head points to + * something within the stack of the current task + */ + if (!object_is_on_stack((void *)task_sp)) + return 0; + + /* + * Follow pointer to tasks kernel stack frame where interrupted + * state was saved. + */ + regs = (struct pt_regs *)task_sp; + pc = regs->cp0_epc; + if (!user_mode(regs) && __kernel_text_address(pc)) { + *sp = regs->regs[29]; + *ra = regs->regs[31]; + return pc; } return 0; } @@ -532,8 +551,7 @@ unsigned long notrace unwind_stack_by_address(unsigned long stack_page, if (leaf < 0) return 0; - if (*sp < stack_page || - *sp + info.frame_size > stack_page + THREAD_SIZE - 32) + if (*sp < low || *sp + info.frame_size > high) return 0; if (leaf) diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index bf83dc1..3de0260 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -924,7 +924,7 @@ asmlinkage void syscall_trace_leave(struct pt_regs *regs) audit_syscall_exit(regs); if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) - trace_sys_exit(regs, regs->regs[2]); + trace_sys_exit(regs, regs_return_value(regs)); if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall_exit(regs, 0); diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index c29d397..e6be1f6 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -371,7 +371,7 @@ EXPORT(sys_call_table) PTR sys_writev PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR sys_ni_syscall /* 4150 */ PTR sys_getsid PTR sys_fdatasync diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S index 0687f96..aa27daf 100644 --- a/arch/mips/kernel/scall64-64.S +++ b/arch/mips/kernel/scall64-64.S @@ -311,7 +311,7 @@ EXPORT(sys_call_table) PTR sys_sched_getaffinity PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR sys_io_setup /* 5200 */ PTR sys_io_destroy PTR sys_io_getevents diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S index 0331ba3..37f608f 100644 --- a/arch/mips/kernel/scall64-n32.S +++ b/arch/mips/kernel/scall64-n32.S @@ -302,7 +302,7 @@ EXPORT(sysn32_call_table) PTR compat_sys_sched_getaffinity PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR compat_sys_io_setup /* 6200 */ PTR sys_io_destroy PTR compat_sys_io_getevents diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index 5a47042..7913a5c 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -371,7 +371,7 @@ EXPORT(sys32_call_table) PTR compat_sys_writev PTR sys_cacheflush PTR sys_cachectl - PTR sys_sysmips + PTR __sys_sysmips PTR sys_ni_syscall /* 4150 */ PTR sys_getsid PTR sys_fdatasync diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c index 6d0f132..47c9646 100644 --- a/arch/mips/kernel/smp-bmips.c +++ b/arch/mips/kernel/smp-bmips.c @@ -587,11 +587,11 @@ void __init bmips_cpu_setup(void) /* Flush and enable RAC */ cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG); - __raw_writel(cfg | 0x100, BMIPS_RAC_CONFIG); + __raw_writel(cfg | 0x100, cbr + BMIPS_RAC_CONFIG); __raw_readl(cbr + BMIPS_RAC_CONFIG); cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG); - __raw_writel(cfg | 0xf, BMIPS_RAC_CONFIG); + __raw_writel(cfg | 0xf, cbr + BMIPS_RAC_CONFIG); __raw_readl(cbr + BMIPS_RAC_CONFIG); cfg = __raw_readl(cbr + BMIPS_RAC_ADDRESS_RANGE); diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 7ebb191..95ba427 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -68,6 +68,9 @@ EXPORT_SYMBOL(cpu_sibling_map); cpumask_t cpu_core_map[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_core_map); +static DECLARE_COMPLETION(cpu_starting); +static DECLARE_COMPLETION(cpu_running); + /* * A logcal cpu mask containing only one VPE per core to * reduce the number of IPIs on large MT systems. @@ -369,9 +372,12 @@ asmlinkage void start_secondary(void) cpumask_set_cpu(cpu, &cpu_coherent_mask); notify_cpu_starting(cpu); - cpumask_set_cpu(cpu, &cpu_callin_map); + /* Notify boot CPU that we're starting & ready to sync counters */ + complete(&cpu_starting); + synchronise_count_slave(cpu); + /* The CPU is running and counters synchronised, now mark it online */ set_cpu_online(cpu, true); set_cpu_sibling_map(cpu); @@ -380,6 +386,12 @@ asmlinkage void start_secondary(void) calculate_cpu_foreign_map(); /* + * Notify boot CPU that we're up & online and it can safely return + * from __cpu_up + */ + complete(&cpu_running); + + /* * irq will be enabled in ->smp_finish(), enabling it too early * is dangerous. */ @@ -430,22 +442,23 @@ void smp_prepare_boot_cpu(void) { set_cpu_possible(0, true); set_cpu_online(0, true); - cpumask_set_cpu(0, &cpu_callin_map); } int __cpu_up(unsigned int cpu, struct task_struct *tidle) { mp_ops->boot_secondary(cpu, tidle); - /* - * Trust is futile. We should really have timeouts ... - */ - while (!cpumask_test_cpu(cpu, &cpu_callin_map)) { - udelay(100); - schedule(); + /* Wait for CPU to start and be ready to sync counters */ + if (!wait_for_completion_timeout(&cpu_starting, + msecs_to_jiffies(1000))) { + pr_crit("CPU%u: failed to start\n", cpu); + return -EIO; } synchronise_count_master(cpu); + + /* Wait for CPU to finish startup & mark itself online before return */ + wait_for_completion(&cpu_running); return 0; } diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c index 53a7ef9..4234b2d 100644 --- a/arch/mips/kernel/syscall.c +++ b/arch/mips/kernel/syscall.c @@ -28,6 +28,7 @@ #include <linux/elf.h> #include <asm/asm.h> +#include <asm/asm-eva.h> #include <asm/branch.h> #include <asm/cachectl.h> #include <asm/cacheflush.h> @@ -138,10 +139,12 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) __asm__ __volatile__ ( " .set "MIPS_ISA_ARCH_LEVEL" \n" " li %[err], 0 \n" - "1: ll %[old], (%[addr]) \n" + "1: \n" + user_ll("%[old]", "(%[addr])") " move %[tmp], %[new] \n" - "2: sc %[tmp], (%[addr]) \n" - " bnez %[tmp], 4f \n" + "2: \n" + user_sc("%[tmp]", "(%[addr])") + " beqz %[tmp], 4f \n" "3: \n" " .insn \n" " .subsection 2 \n" @@ -199,6 +202,12 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new) unreachable(); } +/* + * mips_atomic_set() normally returns directly via syscall_exit potentially + * clobbering static registers, so be sure to preserve them. + */ +save_static_function(sys_sysmips); + SYSCALL_DEFINE3(sysmips, long, cmd, long, arg1, long, arg2) { switch (cmd) { diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index ec87ef9..b0b29cb 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -199,6 +199,8 @@ void show_stack(struct task_struct *task, unsigned long *sp) { struct pt_regs regs; mm_segment_t old_fs = get_fs(); + + regs.cp0_status = KSU_KERNEL; if (sp) { regs.regs[29] = (unsigned long)sp; regs.regs[31] = 0; diff --git a/arch/mips/kernel/vmlinux.lds.S b/arch/mips/kernel/vmlinux.lds.S index d5de675..f0a0e6d 100644 --- a/arch/mips/kernel/vmlinux.lds.S +++ b/arch/mips/kernel/vmlinux.lds.S @@ -182,7 +182,7 @@ SECTIONS * Force .bss to 64K alignment so that .bss..swapper_pg_dir * gets that alignment. .sbss should be empty, so there will be * no holes after __init_end. */ - BSS_SECTION(0, 0x10000, 0) + BSS_SECTION(0, 0x10000, 8) _end = . ; diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c index 9056547..95bec46 100644 --- a/arch/mips/lantiq/xway/sysctrl.c +++ b/arch/mips/lantiq/xway/sysctrl.c @@ -469,8 +469,8 @@ void __init ltq_soc_init(void) panic("Failed to load xbar nodes from devicetree"); if (of_address_to_resource(np_xbar, 0, &res_xbar)) panic("Failed to get xbar resources"); - if (request_mem_region(res_xbar.start, resource_size(&res_xbar), - res_xbar.name) < 0) + if (!request_mem_region(res_xbar.start, resource_size(&res_xbar), + res_xbar.name)) panic("Failed to get xbar resources"); ltq_xbar_membase = ioremap_nocache(res_xbar.start, diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index f8b7bf8..9ade60c 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -2386,7 +2386,6 @@ dcopuop: break; default: /* Reserved R6 ops */ - pr_err("Reserved MIPS R6 CMP.condn.S operation\n"); return SIGILL; } } @@ -2460,7 +2459,6 @@ dcopuop: break; default: /* Reserved R6 ops */ - pr_err("Reserved MIPS R6 CMP.condn.D operation\n"); return SIGILL; } } @@ -2522,6 +2520,35 @@ dcopuop: return 0; } +/* + * Emulate FPU instructions. + * + * If we use FPU hardware, then we have been typically called to handle + * an unimplemented operation, such as where an operand is a NaN or + * denormalized. In that case exit the emulation loop after a single + * iteration so as to let hardware execute any subsequent instructions. + * + * If we have no FPU hardware or it has been disabled, then continue + * emulating floating-point instructions until one of these conditions + * has occurred: + * + * - a non-FPU instruction has been encountered, + * + * - an attempt to emulate has ended with a signal, + * + * - the ISA mode has been switched. + * + * We need to terminate the emulation loop if we got switched to the + * MIPS16 mode, whether supported or not, so that we do not attempt + * to emulate a MIPS16 instruction as a regular MIPS FPU instruction. + * Similarly if we got switched to the microMIPS mode and only the + * regular MIPS mode is supported, so that we do not attempt to emulate + * a microMIPS instruction as a regular MIPS FPU instruction. Or if + * we got switched to the regular MIPS mode and only the microMIPS mode + * is supported, so that we do not attempt to emulate a regular MIPS + * instruction that should cause an Address Error exception instead. + * For simplicity we always terminate upon an ISA mode switch. + */ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, int has_fpu, void *__user *fault_addr) { @@ -2607,6 +2634,15 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx, break; if (sig) break; + /* + * We have to check for the ISA bit explicitly here, + * because `get_isa16_mode' may return 0 if support + * for code compression has been globally disabled, + * or otherwise we may produce the wrong signal or + * even proceed successfully where we must not. + */ + if ((xcp->cp0_epc ^ prevepc) & 0x1) + break; cond_resched(); } while (xcp->cp0_epc > prevepc); diff --git a/arch/mips/math-emu/dp_fmax.c b/arch/mips/math-emu/dp_fmax.c index fd71b8d..5bec64f 100644 --- a/arch/mips/math-emu/dp_fmax.c +++ b/arch/mips/math-emu/dp_fmax.c @@ -47,14 +47,26 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754dp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -80,9 +92,7 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y) return ys ? x : y; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754dp_zero(1); + return ieee754dp_zero(xs & ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; @@ -106,16 +116,32 @@ union ieee754dp ieee754dp_fmax(union ieee754dp x, union ieee754dp y) else if (xs < ys) return x; - /* Compare exponent */ - if (xe > ye) - return x; - else if (xe < ye) - return y; + /* Signs of inputs are equal, let's compare exponents */ + if (xs == 0) { + /* Inputs are both positive */ + if (xe > ye) + return x; + else if (xe < ye) + return y; + } else { + /* Inputs are both negative */ + if (xe > ye) + return y; + else if (xe < ye) + return x; + } - /* Compare mantissa */ + /* Signs and exponents of inputs are equal, let's compare mantissas */ + if (xs == 0) { + /* Inputs are both positive, with equal signs and exponents */ + if (xm <= ym) + return y; + return x; + } + /* Inputs are both negative, with equal signs and exponents */ if (xm <= ym) - return y; - return x; + return x; + return y; } union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y) @@ -147,14 +173,26 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754dp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -164,6 +202,9 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y) /* * Infinity and zero handling */ + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): + return ieee754dp_inf(xs & ys); + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): @@ -171,7 +212,6 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): return x; - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): @@ -180,9 +220,7 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y) return y; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754dp_zero(1); + return ieee754dp_zero(xs & ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; @@ -207,7 +245,11 @@ union ieee754dp ieee754dp_fmaxa(union ieee754dp x, union ieee754dp y) return y; /* Compare mantissa */ - if (xm <= ym) + if (xm < ym) return y; - return x; + else if (xm > ym) + return x; + else if (xs == 0) + return x; + return y; } diff --git a/arch/mips/math-emu/dp_fmin.c b/arch/mips/math-emu/dp_fmin.c index c1072b0..a287b23 100644 --- a/arch/mips/math-emu/dp_fmin.c +++ b/arch/mips/math-emu/dp_fmin.c @@ -47,14 +47,26 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754dp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -80,9 +92,7 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y) return ys ? y : x; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754dp_zero(1); + return ieee754dp_zero(xs | ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; @@ -106,16 +116,32 @@ union ieee754dp ieee754dp_fmin(union ieee754dp x, union ieee754dp y) else if (xs < ys) return y; - /* Compare exponent */ - if (xe > ye) - return y; - else if (xe < ye) - return x; + /* Signs of inputs are the same, let's compare exponents */ + if (xs == 0) { + /* Inputs are both positive */ + if (xe > ye) + return y; + else if (xe < ye) + return x; + } else { + /* Inputs are both negative */ + if (xe > ye) + return x; + else if (xe < ye) + return y; + } - /* Compare mantissa */ + /* Signs and exponents of inputs are equal, let's compare mantissas */ + if (xs == 0) { + /* Inputs are both positive, with equal signs and exponents */ + if (xm <= ym) + return x; + return y; + } + /* Inputs are both negative, with equal signs and exponents */ if (xm <= ym) - return x; - return y; + return y; + return x; } union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y) @@ -147,14 +173,26 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754dp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -164,25 +202,25 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y) /* * Infinity and zero handling */ + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): + return ieee754dp_inf(xs | ys); + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): - return x; + return y; - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM): - return y; + return x; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754dp_zero(1); + return ieee754dp_zero(xs | ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; @@ -207,7 +245,11 @@ union ieee754dp ieee754dp_fmina(union ieee754dp x, union ieee754dp y) return x; /* Compare mantissa */ - if (xm <= ym) + if (xm < ym) + return x; + else if (xm > ym) + return y; + else if (xs == 1) return x; return y; } diff --git a/arch/mips/math-emu/dp_maddf.c b/arch/mips/math-emu/dp_maddf.c index 4a2d03c..e0d9be5 100644 --- a/arch/mips/math-emu/dp_maddf.c +++ b/arch/mips/math-emu/dp_maddf.c @@ -14,22 +14,45 @@ #include "ieee754dp.h" -enum maddf_flags { - maddf_negate_product = 1 << 0, -}; + +/* 128 bits shift right logical with rounding. */ +void srl128(u64 *hptr, u64 *lptr, int count) +{ + u64 low; + + if (count >= 128) { + *lptr = *hptr != 0 || *lptr != 0; + *hptr = 0; + } else if (count >= 64) { + if (count == 64) { + *lptr = *hptr | (*lptr != 0); + } else { + low = *lptr; + *lptr = *hptr >> (count - 64); + *lptr |= (*hptr << (128 - count)) != 0 || low != 0; + } + *hptr = 0; + } else { + low = *lptr; + *lptr = low >> count | *hptr << (64 - count); + *lptr |= (low << (64 - count)) != 0; + *hptr = *hptr >> count; + } +} static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x, union ieee754dp y, enum maddf_flags flags) { int re; int rs; - u64 rm; unsigned lxm; unsigned hxm; unsigned lym; unsigned hym; u64 lrm; u64 hrm; + u64 lzm; + u64 hzm; u64 t; u64 at; int s; @@ -48,52 +71,34 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x, ieee754_clearcx(); - switch (zc) { - case IEEE754_CLASS_SNAN: - ieee754_setcx(IEEE754_INVALID_OPERATION); + /* + * Handle the cases when at least one of x, y or z is a NaN. + * Order of precedence is sNaN, qNaN and z, x, y. + */ + if (zc == IEEE754_CLASS_SNAN) return ieee754dp_nanxcpt(z); - case IEEE754_CLASS_DNORM: - DPDNORMZ; - /* QNAN is handled separately below */ - } - - switch (CLPAIR(xc, yc)) { - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN): - return ieee754dp_nanxcpt(y); - - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): + if (xc == IEEE754_CLASS_SNAN) return ieee754dp_nanxcpt(x); - - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): + if (yc == IEEE754_CLASS_SNAN) + return ieee754dp_nanxcpt(y); + if (zc == IEEE754_CLASS_QNAN) + return z; + if (xc == IEEE754_CLASS_QNAN) + return x; + if (yc == IEEE754_CLASS_QNAN) return y; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF): - return x; + if (zc == IEEE754_CLASS_DNORM) + DPDNORMZ; + /* ZERO z cases are handled separately below */ + switch (CLPAIR(xc, yc)) { /* * Infinity handling */ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): - if (zc == IEEE754_CLASS_QNAN) - return z; ieee754_setcx(IEEE754_INVALID_OPERATION); return ieee754dp_indef(); @@ -102,9 +107,27 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x, case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): - if (zc == IEEE754_CLASS_QNAN) - return z; - return ieee754dp_inf(xs ^ ys); + if ((zc == IEEE754_CLASS_INF) && + ((!(flags & MADDF_NEGATE_PRODUCT) && (zs != (xs ^ ys))) || + ((flags & MADDF_NEGATE_PRODUCT) && (zs == (xs ^ ys))))) { + /* + * Cases of addition of infinities with opposite signs + * or subtraction of infinities with same signs. + */ + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754dp_indef(); + } + /* + * z is here either not an infinity, or an infinity having the + * same sign as product (x*y) (in case of MADDF.D instruction) + * or product -(x*y) (in MSUBF.D case). The result must be an + * infinity, and its sign is determined only by the value of + * (flags & MADDF_NEGATE_PRODUCT) and the signs of x and y. + */ + if (flags & MADDF_NEGATE_PRODUCT) + return ieee754dp_inf(1 ^ (xs ^ ys)); + else + return ieee754dp_inf(xs ^ ys); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM): @@ -113,32 +136,42 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x, case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): if (zc == IEEE754_CLASS_INF) return ieee754dp_inf(zs); - /* Multiplication is 0 so just return z */ + if (zc == IEEE754_CLASS_ZERO) { + /* Handle cases +0 + (-0) and similar ones. */ + if ((!(flags & MADDF_NEGATE_PRODUCT) + && (zs == (xs ^ ys))) || + ((flags & MADDF_NEGATE_PRODUCT) + && (zs != (xs ^ ys)))) + /* + * Cases of addition of zeros of equal signs + * or subtraction of zeroes of opposite signs. + * The sign of the resulting zero is in any + * such case determined only by the sign of z. + */ + return z; + + return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD); + } + /* x*y is here 0, and z is not 0, so just return z */ return z; case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): DPDNORMX; case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) + if (zc == IEEE754_CLASS_INF) return ieee754dp_inf(zs); DPDNORMY; break; case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) + if (zc == IEEE754_CLASS_INF) return ieee754dp_inf(zs); DPDNORMX; break; case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) + if (zc == IEEE754_CLASS_INF) return ieee754dp_inf(zs); /* fall through to real computations */ } @@ -157,7 +190,7 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x, re = xe + ye; rs = xs ^ ys; - if (flags & maddf_negate_product) + if (flags & MADDF_NEGATE_PRODUCT) rs ^= 1; /* shunt to top of word */ @@ -165,7 +198,7 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x, ym <<= 64 - (DP_FBITS + 1); /* - * Multiply 64 bits xm, ym to give high 64 bits rm with stickness. + * Multiply 64 bits xm and ym to give 128 bits result in hrm:lrm. */ /* 32 * 32 => 64 */ @@ -195,78 +228,110 @@ static union ieee754dp _dp_maddf(union ieee754dp z, union ieee754dp x, hrm = hrm + (t >> 32); - rm = hrm | (lrm != 0); - - /* - * Sticky shift down to normal rounding precision. - */ - if ((s64) rm < 0) { - rm = (rm >> (64 - (DP_FBITS + 1 + 3))) | - ((rm << (DP_FBITS + 1 + 3)) != 0); + /* Put explicit bit at bit 126 if necessary */ + if ((int64_t)hrm < 0) { + lrm = (hrm << 63) | (lrm >> 1); + hrm = hrm >> 1; re++; - } else { - rm = (rm >> (64 - (DP_FBITS + 1 + 3 + 1))) | - ((rm << (DP_FBITS + 1 + 3 + 1)) != 0); } - assert(rm & (DP_HIDDEN_BIT << 3)); - /* And now the addition */ - assert(zm & DP_HIDDEN_BIT); + assert(hrm & (1 << 62)); - /* - * Provide guard,round and stick bit space. - */ - zm <<= 3; + if (zc == IEEE754_CLASS_ZERO) { + /* + * Move explicit bit from bit 126 to bit 55 since the + * ieee754dp_format code expects the mantissa to be + * 56 bits wide (53 + 3 rounding bits). + */ + srl128(&hrm, &lrm, (126 - 55)); + return ieee754dp_format(rs, re, lrm); + } + + /* Move explicit bit from bit 52 to bit 126 */ + lzm = 0; + hzm = zm << 10; + assert(hzm & (1 << 62)); + /* Make the exponents the same */ if (ze > re) { /* * Have to shift y fraction right to align. */ s = ze - re; - rm = XDPSRS(rm, s); + srl128(&hrm, &lrm, s); re += s; } else if (re > ze) { /* * Have to shift x fraction right to align. */ s = re - ze; - zm = XDPSRS(zm, s); + srl128(&hzm, &lzm, s); ze += s; } assert(ze == re); assert(ze <= DP_EMAX); + /* Do the addition */ if (zs == rs) { /* - * Generate 28 bit result of adding two 27 bit numbers - * leaving result in xm, xs and xe. + * Generate 128 bit result by adding two 127 bit numbers + * leaving result in hzm:lzm, zs and ze. */ - zm = zm + rm; - - if (zm >> (DP_FBITS + 1 + 3)) { /* carry out */ - zm = XDPSRS1(zm); + hzm = hzm + hrm + (lzm > (lzm + lrm)); + lzm = lzm + lrm; + if ((int64_t)hzm < 0) { /* carry out */ + srl128(&hzm, &lzm, 1); ze++; } } else { - if (zm >= rm) { - zm = zm - rm; + if (hzm > hrm || (hzm == hrm && lzm >= lrm)) { + hzm = hzm - hrm - (lzm < lrm); + lzm = lzm - lrm; } else { - zm = rm - zm; + hzm = hrm - hzm - (lrm < lzm); + lzm = lrm - lzm; zs = rs; } - if (zm == 0) + if (lzm == 0 && hzm == 0) return ieee754dp_zero(ieee754_csr.rm == FPU_CSR_RD); /* - * Normalize to rounding precision. + * Put explicit bit at bit 126 if necessary. */ - while ((zm >> (DP_FBITS + 3)) == 0) { - zm <<= 1; - ze--; + if (hzm == 0) { + /* left shift by 63 or 64 bits */ + if ((int64_t)lzm < 0) { + /* MSB of lzm is the explicit bit */ + hzm = lzm >> 1; + lzm = lzm << 63; + ze -= 63; + } else { + hzm = lzm; + lzm = 0; + ze -= 64; + } + } + + t = 0; + while ((hzm >> (62 - t)) == 0) + t++; + + assert(t <= 62); + if (t) { + hzm = hzm << t | lzm >> (64 - t); + lzm = lzm << t; + ze -= t; } } - return ieee754dp_format(zs, ze, zm); + /* + * Move explicit bit from bit 126 to bit 55 since the + * ieee754dp_format code expects the mantissa to be + * 56 bits wide (53 + 3 rounding bits). + */ + srl128(&hzm, &lzm, (126 - 55)); + + return ieee754dp_format(zs, ze, lzm); } union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x, @@ -278,5 +343,5 @@ union ieee754dp ieee754dp_maddf(union ieee754dp z, union ieee754dp x, union ieee754dp ieee754dp_msubf(union ieee754dp z, union ieee754dp x, union ieee754dp y) { - return _dp_maddf(z, x, y, maddf_negate_product); + return _dp_maddf(z, x, y, MADDF_NEGATE_PRODUCT); } diff --git a/arch/mips/math-emu/ieee754int.h b/arch/mips/math-emu/ieee754int.h index 8bc2f69..dd2071f 100644 --- a/arch/mips/math-emu/ieee754int.h +++ b/arch/mips/math-emu/ieee754int.h @@ -26,6 +26,10 @@ #define CLPAIR(x, y) ((x)*6+(y)) +enum maddf_flags { + MADDF_NEGATE_PRODUCT = 1 << 0, +}; + static inline void ieee754_clearcx(void) { ieee754_csr.cx = 0; diff --git a/arch/mips/math-emu/ieee754sp.h b/arch/mips/math-emu/ieee754sp.h index 8476067..0f63e42 100644 --- a/arch/mips/math-emu/ieee754sp.h +++ b/arch/mips/math-emu/ieee754sp.h @@ -45,6 +45,10 @@ static inline int ieee754sp_finite(union ieee754sp x) return SPBEXP(x) != SP_EMAX + 1 + SP_EBIAS; } +/* 64 bit right shift with rounding */ +#define XSPSRS64(v, rs) \ + (((rs) >= 64) ? ((v) != 0) : ((v) >> (rs)) | ((v) << (64-(rs)) != 0)) + /* 3bit extended single precision sticky right shift */ #define XSPSRS(v, rs) \ ((rs > (SP_FBITS+3))?1:((v) >> (rs)) | ((v) << (32-(rs)) != 0)) diff --git a/arch/mips/math-emu/sp_fmax.c b/arch/mips/math-emu/sp_fmax.c index 4d00084..74a5a00 100644 --- a/arch/mips/math-emu/sp_fmax.c +++ b/arch/mips/math-emu/sp_fmax.c @@ -47,14 +47,26 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754sp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -80,9 +92,7 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y) return ys ? x : y; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754sp_zero(1); + return ieee754sp_zero(xs & ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; @@ -106,16 +116,32 @@ union ieee754sp ieee754sp_fmax(union ieee754sp x, union ieee754sp y) else if (xs < ys) return x; - /* Compare exponent */ - if (xe > ye) - return x; - else if (xe < ye) - return y; + /* Signs of inputs are equal, let's compare exponents */ + if (xs == 0) { + /* Inputs are both positive */ + if (xe > ye) + return x; + else if (xe < ye) + return y; + } else { + /* Inputs are both negative */ + if (xe > ye) + return y; + else if (xe < ye) + return x; + } - /* Compare mantissa */ + /* Signs and exponents of inputs are equal, let's compare mantissas */ + if (xs == 0) { + /* Inputs are both positive, with equal signs and exponents */ + if (xm <= ym) + return y; + return x; + } + /* Inputs are both negative, with equal signs and exponents */ if (xm <= ym) - return y; - return x; + return x; + return y; } union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y) @@ -147,14 +173,26 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754sp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -164,6 +202,9 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y) /* * Infinity and zero handling */ + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): + return ieee754sp_inf(xs & ys); + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): @@ -171,7 +212,6 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): return x; - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): @@ -180,9 +220,7 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y) return y; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754sp_zero(1); + return ieee754sp_zero(xs & ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; @@ -207,7 +245,11 @@ union ieee754sp ieee754sp_fmaxa(union ieee754sp x, union ieee754sp y) return y; /* Compare mantissa */ - if (xm <= ym) + if (xm < ym) return y; - return x; + else if (xm > ym) + return x; + else if (xs == 0) + return x; + return y; } diff --git a/arch/mips/math-emu/sp_fmin.c b/arch/mips/math-emu/sp_fmin.c index 4eb1bb9..c51385f 100644 --- a/arch/mips/math-emu/sp_fmin.c +++ b/arch/mips/math-emu/sp_fmin.c @@ -47,14 +47,26 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754sp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -80,9 +92,7 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y) return ys ? y : x; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754sp_zero(1); + return ieee754sp_zero(xs | ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; @@ -106,16 +116,32 @@ union ieee754sp ieee754sp_fmin(union ieee754sp x, union ieee754sp y) else if (xs < ys) return y; - /* Compare exponent */ - if (xe > ye) - return y; - else if (xe < ye) - return x; + /* Signs of inputs are the same, let's compare exponents */ + if (xs == 0) { + /* Inputs are both positive */ + if (xe > ye) + return y; + else if (xe < ye) + return x; + } else { + /* Inputs are both negative */ + if (xe > ye) + return x; + else if (xe < ye) + return y; + } - /* Compare mantissa */ + /* Signs and exponents of inputs are equal, let's compare mantissas */ + if (xs == 0) { + /* Inputs are both positive, with equal signs and exponents */ + if (xm <= ym) + return x; + return y; + } + /* Inputs are both negative, with equal signs and exponents */ if (xm <= ym) - return x; - return y; + return y; + return x; } union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y) @@ -147,14 +173,26 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y) case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): return ieee754sp_nanxcpt(x); - /* numbers are preferred to NaNs */ + /* + * Quiet NaN handling + */ + + /* + * The case of both inputs quiet NaNs + */ + case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): + return x; + + /* + * The cases of exactly one input quiet NaN (numbers + * are here preferred as returned values to NaNs) + */ case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): return x; - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): @@ -164,25 +202,25 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y) /* * Infinity and zero handling */ + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): + return ieee754sp_inf(xs | ys); + case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): - return x; + return y; - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_DNORM): - return y; + return x; case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): - if (xs == ys) - return x; - return ieee754sp_zero(1); + return ieee754sp_zero(xs | ys); case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; @@ -207,7 +245,11 @@ union ieee754sp ieee754sp_fmina(union ieee754sp x, union ieee754sp y) return x; /* Compare mantissa */ - if (xm <= ym) + if (xm < ym) + return x; + else if (xm > ym) + return y; + else if (xs == 1) return x; return y; } diff --git a/arch/mips/math-emu/sp_maddf.c b/arch/mips/math-emu/sp_maddf.c index a8cd8b4..7195fe7 100644 --- a/arch/mips/math-emu/sp_maddf.c +++ b/arch/mips/math-emu/sp_maddf.c @@ -14,9 +14,6 @@ #include "ieee754sp.h" -enum maddf_flags { - maddf_negate_product = 1 << 0, -}; static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x, union ieee754sp y, enum maddf_flags flags) @@ -24,14 +21,8 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x, int re; int rs; unsigned rm; - unsigned short lxm; - unsigned short hxm; - unsigned short lym; - unsigned short hym; - unsigned lrm; - unsigned hrm; - unsigned t; - unsigned at; + uint64_t rm64; + uint64_t zm64; int s; COMPXSP; @@ -48,51 +39,35 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x, ieee754_clearcx(); - switch (zc) { - case IEEE754_CLASS_SNAN: - ieee754_setcx(IEEE754_INVALID_OPERATION); + /* + * Handle the cases when at least one of x, y or z is a NaN. + * Order of precedence is sNaN, qNaN and z, x, y. + */ + if (zc == IEEE754_CLASS_SNAN) return ieee754sp_nanxcpt(z); - case IEEE754_CLASS_DNORM: - SPDNORMZ; - /* QNAN is handled separately below */ - } - - switch (CLPAIR(xc, yc)) { - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_SNAN): + if (xc == IEEE754_CLASS_SNAN) + return ieee754sp_nanxcpt(x); + if (yc == IEEE754_CLASS_SNAN) return ieee754sp_nanxcpt(y); + if (zc == IEEE754_CLASS_QNAN) + return z; + if (xc == IEEE754_CLASS_QNAN) + return x; + if (yc == IEEE754_CLASS_QNAN) + return y; - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_SNAN): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_SNAN, IEEE754_CLASS_INF): - return ieee754sp_nanxcpt(x); + if (zc == IEEE754_CLASS_DNORM) + SPDNORMZ; + /* ZERO z cases are handled separately below */ - case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_QNAN): - return y; + switch (CLPAIR(xc, yc)) { - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_QNAN): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_ZERO): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_NORM): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_DNORM): - case CLPAIR(IEEE754_CLASS_QNAN, IEEE754_CLASS_INF): - return x; /* * Infinity handling */ case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_INF): - if (zc == IEEE754_CLASS_QNAN) - return z; ieee754_setcx(IEEE754_INVALID_OPERATION); return ieee754sp_indef(); @@ -101,9 +76,27 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x, case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_NORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_DNORM): case CLPAIR(IEEE754_CLASS_INF, IEEE754_CLASS_INF): - if (zc == IEEE754_CLASS_QNAN) - return z; - return ieee754sp_inf(xs ^ ys); + if ((zc == IEEE754_CLASS_INF) && + ((!(flags & MADDF_NEGATE_PRODUCT) && (zs != (xs ^ ys))) || + ((flags & MADDF_NEGATE_PRODUCT) && (zs == (xs ^ ys))))) { + /* + * Cases of addition of infinities with opposite signs + * or subtraction of infinities with same signs. + */ + ieee754_setcx(IEEE754_INVALID_OPERATION); + return ieee754sp_indef(); + } + /* + * z is here either not an infinity, or an infinity having the + * same sign as product (x*y) (in case of MADDF.D instruction) + * or product -(x*y) (in MSUBF.D case). The result must be an + * infinity, and its sign is determined only by the value of + * (flags & MADDF_NEGATE_PRODUCT) and the signs of x and y. + */ + if (flags & MADDF_NEGATE_PRODUCT) + return ieee754sp_inf(1 ^ (xs ^ ys)); + else + return ieee754sp_inf(xs ^ ys); case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_ZERO): case CLPAIR(IEEE754_CLASS_ZERO, IEEE754_CLASS_NORM): @@ -112,32 +105,42 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x, case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_ZERO): if (zc == IEEE754_CLASS_INF) return ieee754sp_inf(zs); - /* Multiplication is 0 so just return z */ + if (zc == IEEE754_CLASS_ZERO) { + /* Handle cases +0 + (-0) and similar ones. */ + if ((!(flags & MADDF_NEGATE_PRODUCT) + && (zs == (xs ^ ys))) || + ((flags & MADDF_NEGATE_PRODUCT) + && (zs != (xs ^ ys)))) + /* + * Cases of addition of zeros of equal signs + * or subtraction of zeroes of opposite signs. + * The sign of the resulting zero is in any + * such case determined only by the sign of z. + */ + return z; + + return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD); + } + /* x*y is here 0, and z is not 0, so just return z */ return z; case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_DNORM): SPDNORMX; case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_DNORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) + if (zc == IEEE754_CLASS_INF) return ieee754sp_inf(zs); SPDNORMY; break; case CLPAIR(IEEE754_CLASS_DNORM, IEEE754_CLASS_NORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) + if (zc == IEEE754_CLASS_INF) return ieee754sp_inf(zs); SPDNORMX; break; case CLPAIR(IEEE754_CLASS_NORM, IEEE754_CLASS_NORM): - if (zc == IEEE754_CLASS_QNAN) - return z; - else if (zc == IEEE754_CLASS_INF) + if (zc == IEEE754_CLASS_INF) return ieee754sp_inf(zs); /* fall through to real computations */ } @@ -158,108 +161,93 @@ static union ieee754sp _sp_maddf(union ieee754sp z, union ieee754sp x, re = xe + ye; rs = xs ^ ys; - if (flags & maddf_negate_product) + if (flags & MADDF_NEGATE_PRODUCT) rs ^= 1; - /* shunt to top of word */ - xm <<= 32 - (SP_FBITS + 1); - ym <<= 32 - (SP_FBITS + 1); - - /* - * Multiply 32 bits xm, ym to give high 32 bits rm with stickness. - */ - lxm = xm & 0xffff; - hxm = xm >> 16; - lym = ym & 0xffff; - hym = ym >> 16; - - lrm = lxm * lym; /* 16 * 16 => 32 */ - hrm = hxm * hym; /* 16 * 16 => 32 */ + /* Multiple 24 bit xm and ym to give 48 bit results */ + rm64 = (uint64_t)xm * ym; - t = lxm * hym; /* 16 * 16 => 32 */ - at = lrm + (t << 16); - hrm += at < lrm; - lrm = at; - hrm = hrm + (t >> 16); + /* Shunt to top of word */ + rm64 = rm64 << 16; - t = hxm * lym; /* 16 * 16 => 32 */ - at = lrm + (t << 16); - hrm += at < lrm; - lrm = at; - hrm = hrm + (t >> 16); - - rm = hrm | (lrm != 0); - - /* - * Sticky shift down to normal rounding precision. - */ - if ((int) rm < 0) { - rm = (rm >> (32 - (SP_FBITS + 1 + 3))) | - ((rm << (SP_FBITS + 1 + 3)) != 0); + /* Put explicit bit at bit 62 if necessary */ + if ((int64_t) rm64 < 0) { + rm64 = rm64 >> 1; re++; - } else { - rm = (rm >> (32 - (SP_FBITS + 1 + 3 + 1))) | - ((rm << (SP_FBITS + 1 + 3 + 1)) != 0); } - assert(rm & (SP_HIDDEN_BIT << 3)); - /* And now the addition */ + assert(rm64 & (1 << 62)); - assert(zm & SP_HIDDEN_BIT); + if (zc == IEEE754_CLASS_ZERO) { + /* + * Move explicit bit from bit 62 to bit 26 since the + * ieee754sp_format code expects the mantissa to be + * 27 bits wide (24 + 3 rounding bits). + */ + rm = XSPSRS64(rm64, (62 - 26)); + return ieee754sp_format(rs, re, rm); + } - /* - * Provide guard,round and stick bit space. - */ - zm <<= 3; + /* Move explicit bit from bit 23 to bit 62 */ + zm64 = (uint64_t)zm << (62 - 23); + assert(zm64 & (1 << 62)); + /* Make the exponents the same */ if (ze > re) { /* * Have to shift r fraction right to align. */ s = ze - re; - rm = XSPSRS(rm, s); + rm64 = XSPSRS64(rm64, s); re += s; } else if (re > ze) { /* * Have to shift z fraction right to align. */ s = re - ze; - zm = XSPSRS(zm, s); + zm64 = XSPSRS64(zm64, s); ze += s; } assert(ze == re); assert(ze <= SP_EMAX); + /* Do the addition */ if (zs == rs) { /* - * Generate 28 bit result of adding two 27 bit numbers - * leaving result in zm, zs and ze. + * Generate 64 bit result by adding two 63 bit numbers + * leaving result in zm64, zs and ze. */ - zm = zm + rm; - - if (zm >> (SP_FBITS + 1 + 3)) { /* carry out */ - zm = XSPSRS1(zm); + zm64 = zm64 + rm64; + if ((int64_t)zm64 < 0) { /* carry out */ + zm64 = XSPSRS1(zm64); ze++; } } else { - if (zm >= rm) { - zm = zm - rm; + if (zm64 >= rm64) { + zm64 = zm64 - rm64; } else { - zm = rm - zm; + zm64 = rm64 - zm64; zs = rs; } - if (zm == 0) + if (zm64 == 0) return ieee754sp_zero(ieee754_csr.rm == FPU_CSR_RD); /* - * Normalize in extended single precision + * Put explicit bit at bit 62 if necessary. */ - while ((zm >> (SP_MBITS + 3)) == 0) { - zm <<= 1; + while ((zm64 >> 62) == 0) { + zm64 <<= 1; ze--; } - } + + /* + * Move explicit bit from bit 62 to bit 26 since the + * ieee754sp_format code expects the mantissa to be + * 27 bits wide (24 + 3 rounding bits). + */ + zm = XSPSRS64(zm64, (62 - 26)); + return ieee754sp_format(zs, ze, zm); } @@ -272,5 +260,5 @@ union ieee754sp ieee754sp_maddf(union ieee754sp z, union ieee754sp x, union ieee754sp ieee754sp_msubf(union ieee754sp z, union ieee754sp x, union ieee754sp y) { - return _sp_maddf(z, x, y, maddf_negate_product); + return _sp_maddf(z, x, y, MADDF_NEGATE_PRODUCT); } diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c index 277cf52..6c17cba 100644 --- a/arch/mips/mm/uasm-micromips.c +++ b/arch/mips/mm/uasm-micromips.c @@ -80,7 +80,7 @@ static struct insn insn_table_MM[] = { { insn_jr, M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RS }, { insn_lb, M(mm_lb32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, { insn_ld, 0, 0 }, - { insn_lh, M(mm_lh32_op, 0, 0, 0, 0, 0), RS | RS | SIMM }, + { insn_lh, M(mm_lh32_op, 0, 0, 0, 0, 0), RT | RS | SIMM }, { insn_ll, M(mm_pool32c_op, 0, 0, (mm_ll_func << 1), 0, 0), RS | RT | SIMM }, { insn_lld, 0, 0 }, { insn_lui, M(mm_pool32i_op, mm_lui_op, 0, 0, 0, 0), RS | SIMM }, diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c index 3c7c9bf..6f892c1 100644 --- a/arch/mips/ralink/mt7620.c +++ b/arch/mips/ralink/mt7620.c @@ -176,7 +176,7 @@ static struct rt2880_pmx_func spi_cs1_grp_mt7628[] = { static struct rt2880_pmx_func spis_grp_mt7628[] = { FUNC("pwm_uart2", 3, 14, 4), - FUNC("util", 2, 14, 4), + FUNC("utif", 2, 14, 4), FUNC("gpio", 1, 14, 4), FUNC("spis", 0, 14, 4), }; @@ -190,28 +190,28 @@ static struct rt2880_pmx_func gpio_grp_mt7628[] = { static struct rt2880_pmx_func p4led_kn_grp_mt7628[] = { FUNC("jtag", 3, 30, 1), - FUNC("util", 2, 30, 1), + FUNC("utif", 2, 30, 1), FUNC("gpio", 1, 30, 1), FUNC("p4led_kn", 0, 30, 1), }; static struct rt2880_pmx_func p3led_kn_grp_mt7628[] = { FUNC("jtag", 3, 31, 1), - FUNC("util", 2, 31, 1), + FUNC("utif", 2, 31, 1), FUNC("gpio", 1, 31, 1), FUNC("p3led_kn", 0, 31, 1), }; static struct rt2880_pmx_func p2led_kn_grp_mt7628[] = { FUNC("jtag", 3, 32, 1), - FUNC("util", 2, 32, 1), + FUNC("utif", 2, 32, 1), FUNC("gpio", 1, 32, 1), FUNC("p2led_kn", 0, 32, 1), }; static struct rt2880_pmx_func p1led_kn_grp_mt7628[] = { FUNC("jtag", 3, 33, 1), - FUNC("util", 2, 33, 1), + FUNC("utif", 2, 33, 1), FUNC("gpio", 1, 33, 1), FUNC("p1led_kn", 0, 33, 1), }; @@ -232,28 +232,28 @@ static struct rt2880_pmx_func wled_kn_grp_mt7628[] = { static struct rt2880_pmx_func p4led_an_grp_mt7628[] = { FUNC("jtag", 3, 39, 1), - FUNC("util", 2, 39, 1), + FUNC("utif", 2, 39, 1), FUNC("gpio", 1, 39, 1), FUNC("p4led_an", 0, 39, 1), }; static struct rt2880_pmx_func p3led_an_grp_mt7628[] = { FUNC("jtag", 3, 40, 1), - FUNC("util", 2, 40, 1), + FUNC("utif", 2, 40, 1), FUNC("gpio", 1, 40, 1), FUNC("p3led_an", 0, 40, 1), }; static struct rt2880_pmx_func p2led_an_grp_mt7628[] = { FUNC("jtag", 3, 41, 1), - FUNC("util", 2, 41, 1), + FUNC("utif", 2, 41, 1), FUNC("gpio", 1, 41, 1), FUNC("p2led_an", 0, 41, 1), }; static struct rt2880_pmx_func p1led_an_grp_mt7628[] = { FUNC("jtag", 3, 42, 1), - FUNC("util", 2, 42, 1), + FUNC("utif", 2, 42, 1), FUNC("gpio", 1, 42, 1), FUNC("p1led_an", 0, 42, 1), }; diff --git a/arch/mips/ralink/rt3883.c b/arch/mips/ralink/rt3883.c index 9e4631a..3e68e35 100644 --- a/arch/mips/ralink/rt3883.c +++ b/arch/mips/ralink/rt3883.c @@ -145,5 +145,5 @@ void prom_soc_init(struct ralink_soc_info *soc_info) rt2880_pinmux_data = rt3883_pinmux_data; - ralink_soc == RT3883_SOC; + ralink_soc = RT3883_SOC; } |